Electroencephalogram signal adaptive recognition method and system, storage medium and electronic device

Abstract

The application provides an electroencephalogram adaptive recognition method and system, a storage medium and an electronic device, comprising: preprocessing SSVEP electroencephalogram signals to obtain effective SSVEP electroencephalogram signals; based on a filter bank canonical correlation analysis algorithm, replacing each sub-band corresponding filter with M candidate filters, and based on the candidate filters, extracting a correlation coefficient group of each sub-band of the effective SSVEP electroencephalogram signals for each stimulation target; obtaining a normalized correlation coefficient group; selecting a sub-filter of each sub-band based on the normalized correlation coefficient group; calculating a sub-band correlation coefficient of the SSVEP electroencephalogram signals for each stimulation target, and selecting a stimulation target corresponding to a maximum value of the sub-band correlation coefficient as a recognition result. The electroencephalogram adaptive recognition method and system, the storage medium and the electronic device can better adapt to the recognition of different types of electroencephalogram signals by dynamically adjusting filter bank parameters.

Description

Adaptive EEG signal recognition methods and systems, storage media and electronic devices Technical Field

[0001] This invention relates to the technical field of brain-computer interfaces (BCI), and in particular to an adaptive brain signal recognition method and system, storage medium and electronic device. Background Technology

[0002] In the field of brain-computer interfaces, electroencephalograms (EEGs), as an important method of recording neural signals, provide a key data source for the development of human-computer interaction and brain control technologies. EEG signals carry information about the brain's electrical activity, and their analysis and interpretation are of great significance for understanding cognitive processes, neural plasticity, and brain dysfunction.

[0003] In brain-computer interface (BCI) technology, canonical correlation analysis (CCA), a widely used statistical method, is employed to explore the correlations between multivariate data and is extensively used for feature extraction and classification prediction of EEG signals. However, while traditional CCA has demonstrated certain advantages in brain-computer interface tasks, it still has limitations in some cases when analyzing complex EEG signals.

[0004] Filter Bank Canonical Correlation Analysis (FBCCA), as an optimized method of CCA, represents a significant advancement in the exploration of better ways to interpret electroencephalogram (EEG) signals. It converts the raw EEG signal into sub-band signals of different frequency bands by applying a set of filters, and then calculates the correlation coefficients between these sub-band signals and a reference signal. The final correlation coefficient is obtained by weighted summation of the correlation coefficients obtained from different sub-bands, thereby extracting valuable information and features from different frequency bands.

[0005] However, FBCCA also has problems and drawbacks in practical applications, one significant issue being the fixed filter bank. In FBCCA, the filter bank settings are predefined, meaning a fixed set of filters is used to process all types of EEG signals. However, EEG signals may contain different information and features in different frequency bands, and these features may vary for different tasks and individuals. Therefore, using a fixed filter bank may cause FBCCA to perform poorly when adapting to different tasks and individuals, limiting its flexibility and generalization ability in practical applications. Summary of the Invention

[0006] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide an adaptive EEG signal recognition method and system, storage medium and electronic device, which dynamically adjusts the filter bank parameters so that the filter bank can be adaptively adjusted according to signal characteristics and task requirements, thereby better adapting to the recognition of different types of EEG signals.

[0007] In a first aspect, the present invention provides an adaptive recognition method for electroencephalogram (EEG) signals, the method comprising the following steps: acquiring SSVEP EEG signals; preprocessing the SSVEP EEG signals to obtain valid SSVEP EEG signals; and, based on a filter bank canonical correlation analysis algorithm, replacing the filter corresponding to each sub-band with M candidate filters, and extracting the correlation coefficient group of each sub-band of the valid SSVEP EEG signal for each stimulus target based on the candidate filters. Where k = 1, 2, ..., K, m = 1, 2, ..., M, k is the index of the stimulus target, K is the number of stimulus targets, and m is the index of the candidate filter; for the correlation array Perform normalization processing to obtain the normalized correlation array. Based on the normalized correlation array, the confidence parameter of each candidate filter in each sub-band is calculated, and the candidate filter with the smallest confidence parameter in each sub-band is selected as the sub-filter of that sub-band; the sub-band correlation coefficient of the SSVEP EEG signal for each stimulus target is calculated. The stimulus target corresponding to the maximum value of the sub-band correlation coefficient is selected as the recognition result, where Let w(n) represent the normalized correlation coefficient of the nth sub-filter with respect to the kth stimulus target, N represent the number of sub-filters, and w(n) represent the weight coefficient of the nth sub-filter.

[0008] In one implementation of the first aspect, acquiring SSVEP EEG signals includes the following steps:

[0009] Displaying the target stimulus paradigm;

[0010] SSVEP brainwave signals generated when subjects view the target stimulus paradigm are collected using an EEG acquisition device.

[0011] In one implementation of the first aspect, preprocessing the SSVEP EEG signal includes the following steps:

[0012] The SSVEP EEG signal was downsampled to 250Hz;

[0013] Bandpass filtering and 50Hz notch filtering were applied to the downsampled SSVEP EEG signal.

[0014] In one implementation of the first aspect, extracting the correlation coefficient set of each sub-band of the effective SSVEP EEG signal for each stimulus target based on the candidate filter includes the following steps:

[0015] For each sub-band, the effective SSVEP EEG signal is filtered based on each candidate filter;

[0016] For each stimulus target, canonical correlation analysis is performed on the filtered effective SSVEP EEG signals to obtain the corresponding correlation array.

[0017] In one implementation of the first aspect, according to Obtain the normalized correlation array.

[0018] In one implementation of the first aspect, according to Calculate the confidence parameter of each candidate filter in each subband, where max is the maximum value and 2ndmax is the second largest value.

[0019] In one implementation of the first aspect, the weight coefficient w(n) of the nth sub-filter is n -1.25 +0.25.

[0020] In a second aspect, the present invention provides an adaptive EEG signal recognition system, the system comprising an acquisition module, a preprocessing module, an extraction module, a normalization module, a reliability module, and a recognition module;

[0021] The acquisition module is used to acquire SSVEP EEG signals;

[0022] The preprocessing module is used to preprocess the SSVEP EEG signal to obtain a valid SSVEP EEG signal.

[0023] The extraction module is used to replace the filter corresponding to each sub-band with M candidate filters based on the filter bank canonical correlation analysis algorithm, and extract the correlation coefficient group of each sub-band of the effective SSVEP EEG signal for each stimulus target based on the candidate filters. Where k = 1, 2, ..., K, m = 1, 2, ..., M, k is the index of the stimulus target, K is the number of stimulus targets, and m is the index of the candidate filter;

[0024] The normalization module is used to normalize the correlation array. Perform normalization processing to obtain the normalized correlation array.

[0025] The confidence module is used to calculate the confidence parameters of each candidate filter in each subband based on the normalized correlation array for each stimulus target, and select the candidate filter with the smallest confidence parameter as the sub-filter of the subband.

[0026] The recognition module is used to calculate the sub-band correlation coefficient of the SSVEP EEG signal for each stimulus target. The stimulus target corresponding to the maximum value of the sub-band correlation coefficient is selected as the recognition result, where Let w(n) represent the normalized correlation coefficient of the nth sub-filter with respect to the kth stimulus target, N represent the number of sub-filters, and w(n) represent the weight coefficient of the nth sub-filter.

[0027] Thirdly, the present invention provides a storage medium on which a computer program is stored, which, when executed by a processor, implements the above-described adaptive EEG signal recognition method.

[0028] Fourthly, the present invention provides an electronic device, comprising: a processor and a memory;

[0029] The memory is used to store computer programs;

[0030] The processor is used to execute the computer program stored in the memory, so that the electronic device performs the above-described adaptive EEG signal recognition method.

[0031] As described above, the adaptive EEG signal recognition method and system, storage medium, and electronic device of the present invention have the following beneficial effects:

[0032] (1) By introducing an adaptive filter bank to dynamically adjust the filter bank parameters, the filter bank can be adaptively adjusted according to signal characteristics and task requirements, thereby better adapting to the recognition of different types of EEG signals.

[0033] (2) Compared with the traditional FBCCA, it is more flexible in adapting to different tasks and individuals and can better capture changes and differences in individual EEG signals;

[0034] (3) Effectively improve the performance of the algorithm in brain-computer interface tasks, thereby bringing greater application potential to fields such as brain control technology, cognitive research and medical applications; bring new breakthroughs to the research and application of brain-computer interface, and provide more possibilities for human-computer interaction and rehabilitation therapy. Attached Figure Description

[0035] Figure 1 shows a flowchart of an embodiment of the adaptive EEG signal recognition method of the present invention;

[0036] Figure 2 shows a schematic diagram of the framework of the adaptive EEG signal recognition method of the present invention in one embodiment;

[0037] Figure 3 shows a schematic diagram of the stimulation paradigm used in this invention in one embodiment;

[0038] Figure 4 shows a schematic diagram of the candidate filters corresponding to each sub-band used in this invention in one embodiment;

[0039] Figure 5 shows a schematic diagram of the structure of the adaptive EEG signal recognition system of the present invention in one embodiment;

[0040] Figure 6 shows a schematic diagram of the structure of the electronic device of the present invention in one embodiment. Detailed Implementation

[0041] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0042] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0043] The following embodiments of the present invention provide an adaptive EEG signal recognition method, which can be applied to electronic devices. The electronic devices described in this invention may include mobile phones with wireless charging capabilities, tablet computers, laptops, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc. The embodiments of the present invention do not impose any limitations on the specific type of electronic device.

[0044] For example, the electronic device may be a station (STAION, ST) in a WLAN with wireless charging capability, a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA) device, handheld device with wireless charging capability, computing device or other processing device, computer, laptop computer, handheld communication device, handheld computing device, and / or other devices for communication over a wireless system, as well as next-generation communication systems, such as mobile terminals in 5G networks, mobile terminals in future evolved Public Land Mobile Networks (PLMNs), or mobile terminals in future evolved Non-terrestrial Networks (NTNs).

[0045] For example, the electronic device can communicate with networks and other devices wirelessly. The wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile Communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), BT, GNSS, WLAN, NFC, FM, and / or IR technologies. The GNSS can include Global Positioning System (GPS), Global Navigation Satellite System (GLONASS), BeiDou Navigation Satellite System (BDS), Quasi-Zenith Satellite System (QZSS), and / or Satellite Based Augmentation Systems (SBAS).

[0046] The technical solutions of the present invention will now be described in detail with reference to the accompanying drawings.

[0047] As shown in Figures 1 and 2, in one embodiment, the adaptive EEG signal recognition method of the present invention includes steps S1-S6.

[0048] Step S1: Obtain SSVEP EEG signals.

[0049] Specifically, steady-state visual evoked potentials (SSVEPs) are a special type of visual evoked potential. They are evoked by visual stimuli with a fixed frequency. When visual stimuli are presented periodically at a specific frequency (such as flashing, image flipping, image scaling, etc.), the visual system is affected and produces an evoked response with stable frequency characteristics. This evoked response typically contains a frequency component of the same frequency as the stimulus and its higher harmonic components.

[0050] In this invention, a selected SSVEP stimulation paradigm is used to display flashing stimuli on a screen, and the SSVEP generated by the subject while viewing the stimulus is collected using an EEG acquisition device. For example, the 40-target stimulus interface shown in Figure 3 is used as the stimulation paradigm. It should be noted that other stimulation paradigms can also be used, and this invention does not impose detailed limitations on the stimulation paradigm.

[0051] In one embodiment, the sampling rate for acquiring EEG signals is 1000 Hz. Using the 10-20 system electrode placement standard, nine electrodes (Pz, PO5, PO3, POz, PO4, PO6, O1, Oz, and O2) are placed in the parietal and occipital lobe regions to record SSVEP signals. A reference electrode is located at the apex (Cz) position, and the electrode impedance is kept below 10 kΩ.

[0052] Step S2: Preprocess the SSVEP EEG signal to obtain a valid SSVEP EEG signal.

[0053] Specifically, the SSVEP EEG signal is preprocessed to remove noise and highlight the effective signal. This includes downsampling the SSVEP EEG signal to 250Hz to reduce computational complexity, applying bandpass filtering to retain the signal within the frequency range of interest, and applying a 50Hz notch filter to eliminate power line interference.

[0054] Step S3: Based on the filter bank canonical correlation analysis algorithm, replace the filter corresponding to each sub-band with M candidate filters, and extract the correlation coefficient group of each sub-band of the effective SSVEP EEG signal for each stimulus target based on the candidate filters. Where k = 1, 2, ..., K, m = 1, 2, ..., M, k is the index of the stimulus target, K is the number of stimulus targets, and m is the index of the candidate filter. M is a natural number not less than 2.

[0055] Specifically, a filter bank canonical correlation analysis algorithm is used to extract EEG signal features related to the stimulation frequency of the stimulus target, i.e., the correlation coefficients of each sub-band of the effective SSVEP EEG signal with respect to each stimulus target. In this invention, to overcome the fixed nature of the filter bank in the filter bank canonical correlation analysis algorithm, an adaptive filter bank is introduced to dynamically adjust the filter bank to meet different EEG signal features. As shown in Figure 4, each sub-band (SB1, SB2…SB…) in the filter bank of the filter bank canonical correlation analysis algorithm is used to… N The corresponding sub-filter is replaced with M candidate filters.

[0056] In one embodiment, extracting the correlation coefficient set of each sub-band of the effective SSVEP EEG signal for each stimulus target based on the candidate filter includes the following steps:

[0057] 31) For each subband, the effective SSVEP EEG signal is filtered based on each candidate filter.

[0058] 32) For each stimulus target, perform canonical correlation analysis on the filtered effective SSVEP EEG signal to obtain the corresponding correlation array. k=1,2,…,K, m=1,2,…,M.

[0059] Step S4: Process the correlation array Perform normalization processing to obtain the normalized correlation array.

[0060] Specifically, L1 normalization is performed on each correlation coefficient array. Since all correlation coefficients ρ are positive, their absolute values ​​can be ignored. Therefore, according to... Obtain the normalized correlation array.

[0061] Step S5: Calculate the confidence parameter of each candidate filter in each subband based on the normalized correlation array, and select the candidate filter with the smallest confidence parameter in each subband as the sub-filter of the subband.

[0062] Specifically, the confidence parameter γ can be obtained from the cross-entropy loss function. γ is negative, and the smaller γ is, the higher the confidence.

[0063] In one embodiment, according to Calculate the confidence parameter of each candidate filter in each subband, where max is the maximum value and 2ndmax is the second largest value.

[0064] According to SB n =argmin m {γ m Let m = 1, 2, ..., M, n = 1, 2, ..., N, and select the sub-filters of the sub-band. Here, n is the sub-filter index, and N is the number of sub-filters.

[0065] Step S6: Calculate the sub-band correlation coefficient of the SSVEP EEG signal for each stimulus target. The stimulus target corresponding to the maximum value of the sub-band correlation coefficient is selected as the recognition result, where Let w(n) represent the normalized correlation coefficient of the nth sub-filter with respect to the kth stimulus target, N represent the number of sub-filters, and w(n) represent the weight coefficient of the nth sub-filter.

[0066] Specifically, the normalized correlation coefficient corresponding to the sub-filter is used as the sub-filter correlation coefficient. For each stimulus target, the weighted sum of the correlation coefficients of the sub-filters is calculated as the sub-band correlation coefficient, i.e. Finally, the maximum value of the subband correlation coefficient is selected. The corresponding stimulus target is used as the recognition result.

[0067] In one embodiment, since the signal-to-noise ratio of the SSVEP harmonic components decreases with increasing frequency, the weighting coefficient w(n) = n -1.25 +0.25.

[0068] The adaptive EEG signal recognition method of the present invention will be further illustrated below through specific embodiments.

[0069] In this embodiment, the target stimulus interface shown in Figure 3 is first selected. Then, a flashing stimulus is displayed on the screen, and the SSVEP generated by the subject while viewing the stimulus is acquired using an EEG acquisition device. For example, a NeuroscanSynAmps 264-256-channel EEG acquisition system is used. The sampling rate for acquiring EEG signals is 1000 Hz, and the electrode arrangement conforms to the 10-20 system electrode arrangement standard. Nine electrodes (Pz, PO5, PO3, POz, PO4, PO6, O1, Oz, and O2) are placed in the parietal and occipital lobe regions to record SSVEP EEG signals. The reference electrode is located at the apex (Cz) position, and the electrode impedance is kept below 10 kΩ.

[0070] After obtaining the SSVEP EEG signal, it needs to be preprocessed to remove noise and highlight the effective signal. Preprocessing includes downsampling the EEG signal to 250Hz to reduce computational complexity and applying a 50Hz notch filter to eliminate power line interference. Since the FBCCA algorithm includes a filter bank, bandpass filtering may not be necessary during preprocessing.

[0071] After preprocessing, an adaptive FBCCA algorithm was used to extract EEG signal features related to the stimulation frequency. First, to overcome the fixed nature of the filter bank in the FBCCA algorithm, each sub-filter in the filter bank was further divided into 10 candidate filters (as shown in Figure 2). The specific candidate filter settings are shown in Table 1, where n is 1 to 5, representing the sub-filter number.

[0072] Table 1. Candidate Filter Parameters

[0073]

[0074] The raw EEG signal was filtered individually using each candidate filter. Then, standard canonical correlation analysis was applied to each component, yielding 10 sets of correlation coefficients for each subband. k=1,2,…,40, m=1,2,…,10.

[0075] L1 normalization is used to normalize the correlation coefficients of each group. Since all correlation coefficients ρ>0, their absolute values ​​can be ignored. Therefore, the normalized correlation coefficient array is...

[0076] The confidence parameter can be obtained from the cross-entropy loss function.

[0077] For each subband, the candidate filter with the smallest γ (i.e., the highest confidence) is selected as the sub-filter. There are a total of 5 sub-filters, namely SB. n =argmin m {γ m ,m=1,2,…,10},n=1,2,…,5.

[0078] Use the correlation coefficients with the smallest γ as the filter correlation coefficients. k=1,2,…,40, n=1,2,…,5.

[0079] The final subband correlation coefficient is obtained by taking the weighted sum of squares of the correlation coefficients of all filters.

[0080] Finally, take the correlation coefficient. The largest target is used as the identification result, which represents the most likely stimulus frequency, i.e.

[0081] The scope of protection of the adaptive EEG signal recognition method described in this embodiment is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principle of this invention is included within the scope of protection of this invention.

[0082] This invention also provides an adaptive EEG signal recognition system, which can implement the adaptive EEG signal recognition method described in this invention. However, the implementation device of the adaptive EEG signal recognition system described in this invention includes, but is not limited to, the structure of the adaptive EEG signal recognition system listed in this embodiment. All structural modifications and substitutions of the prior art made in accordance with the principles of this invention are included within the protection scope of this invention.

[0083] As shown in Figure 5, in one embodiment, the EEG signal adaptive recognition system of the present invention includes an acquisition module 51, a preprocessing module 52, an extraction module 53, a normalization module 54, a reliability module 55, and a recognition module 56.

[0084] The acquisition module 51 is used to acquire SSVEP EEG signals.

[0085] The preprocessing module 52 is connected to the acquisition module 51 and is used to preprocess the SSVEP EEG signal to obtain a valid SSVEP EEG signal.

[0086] The extraction module 53 is connected to the preprocessing module 52 and is used to replace the filter corresponding to each sub-band with M candidate filters based on the filter bank canonical correlation analysis algorithm, and extract the correlation coefficient group of each sub-band of the effective SSVEP EEG signal for each stimulus target based on the candidate filters. Where k = 1, 2, ..., K, m = 1, 2, ..., M, k is the index of the stimulus target, K is the number of stimulus targets, and m is the index of the candidate filter.

[0087] The normalization module 54 is connected to the extraction module 53 and is used to process the correlation array. Perform normalization processing to obtain the normalized correlation array.

[0088] The confidence module 55 is connected to the normalization module 54 and is used to calculate the confidence parameters of each candidate filter in each sub-band based on the normalized correlation array for each stimulus target, and select the candidate filter with the smallest confidence parameter as the sub-filter of the sub-band.

[0089] The identification module 56 is connected to the reliability module 55 and is used to calculate the sub-band correlation coefficient of the SSVEP EEG signal for each stimulus target. The stimulus target corresponding to the maximum value of the sub-band correlation coefficient is selected as the recognition result, where Let w(n) represent the normalized correlation coefficient of the nth sub-filter with respect to the kth stimulus target, N represent the number of sub-filters, and w(n) represent the weight coefficient of the nth sub-filter.

[0090] The structure and principle of the acquisition module 51, preprocessing module 52, extraction module 53, normalization module 54, credibility module 55 and recognition module 56 correspond one-to-one with the steps in the above-mentioned adaptive EEG signal recognition method, so they will not be described in detail here.

[0091] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0092] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of the present invention, depending on actual needs. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0093] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0094] This invention also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the adaptive EEG signal recognition method of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disc, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. This available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0095] This invention also provides an electronic device. The electronic device includes a processor and a memory.

[0096] The memory is used to store computer programs.

[0097] The memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0098] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the electronic device performs the above-described adaptive EEG signal recognition method.

[0099] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0100] As shown in Figure 6, the electronic device of the present invention is embodied in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors or processing units 61, a memory 62, and a bus 63 connecting different system components (including the memory 62 and the processing unit 61).

[0101] Bus 63 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0102] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0103] Memory 62 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 621 and / or cache memory 622. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 623 may be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard disk drive"). Although not shown in FIG. 6, disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disk drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 63 via one or more data media interfaces. Memory 62 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0104] A program / utility 624 having a set (at least one) of program modules 6241 may be stored, for example, in memory 62. Such program modules 6241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 6241 typically perform the functions and / or methods described in the embodiments of the present invention.

[0105] The electronic device can also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 64. Furthermore, the electronic device can communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 65. As shown in Figure 6, network adapter 65 communicates with other modules of the electronic device via bus 63. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0106] In summary, the adaptive EEG signal recognition method and system, storage medium, and electronic device of this invention dynamically adjust the filter bank parameters by introducing an adaptive filter bank. This allows the filter bank to adapt to signal characteristics and task requirements, thus better adapting to the recognition of different types of EEG signals. Compared with traditional FBCCA, it is more flexible in adapting to different tasks and individuals, and can better capture changes and differences in individual EEG signals. It effectively improves the performance of the algorithm in brain-computer interface tasks, thereby bringing greater application potential to fields such as brain control technology, cognitive research, and medical applications. It brings new breakthroughs to the research and application of brain-computer interfaces, and provides more possibilities for human-computer interaction and rehabilitation therapy. Therefore, this invention effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0107] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. An adaptive brainwave signal recognition method, characterized in that, The method includes the following steps: acquiring SSVEP EEG signals; preprocessing the SSVEP EEG signals to obtain valid SSVEP EEG signals; and, based on a filter bank canonical correlation analysis algorithm, replacing the filter corresponding to each sub-band with M candidate filters, and extracting the correlation coefficient groups of each sub-band of the valid SSVEP EEG signals for each stimulus target based on the candidate filters. ,in k is the index of the stimulus target, K is the number of stimulus targets, and m is the index of the candidate filter; for the correlation array Perform normalization processing to obtain the normalized correlation array. Based on the normalized correlation array, the confidence parameter of each candidate filter in each sub-band is calculated, and the candidate filter with the smallest confidence parameter in each sub-band is selected as the sub-filter of that sub-band; according to Calculate the confidence parameter for each candidate filter in each subband, where The maximum value, The second largest value; calculate the sub-band correlation coefficient of the SSVEP EEG signal for each stimulus target. The stimulus target corresponding to the maximum subband correlation coefficient is selected as the recognition result, whereby... This represents the normalized correlation coefficient of the nth sub-filter with respect to the kth stimulus target, where N represents the number of sub-filters. This represents the weight coefficient of the nth sub-filter.

2. The adaptive EEG signal recognition method according to claim 1, characterized in that, Acquiring SSVEP EEG signals includes the following steps: displaying the target stimulus paradigm; and acquiring SSVEP EEG signals generated when the subject views the target stimulus paradigm using an EEG acquisition device.

3. The adaptive EEG signal recognition method according to claim 1, characterized in that, The preprocessing of the SSVEP EEG signal includes the following steps: downsampling the SSVEP EEG signal to 250Hz; and performing bandpass filtering and 50Hz notch filtering on the downsampled SSVEP EEG signal.

4. The adaptive EEG signal recognition method according to claim 1, characterized in that, Extracting the correlation coefficient set of each sub-band of the effective SSVEP EEG signal for each stimulus target based on the candidate filter includes the following steps: for each sub-band, filtering the effective SSVEP EEG signal based on each candidate filter; for each stimulus target, performing canonical correlation analysis on the filtered effective SSVEP EEG signal to obtain the corresponding correlation coefficient set.

5. The adaptive EEG signal recognition method according to claim 1, characterized in that, according to Obtain the normalized correlation array.

6. The adaptive EEG signal recognition method according to claim 1, characterized in that, The weight coefficients of the nth sub-filter 。 7. An adaptive EEG signal recognition system, characterized in that, The system includes an acquisition module, a preprocessing module, an extraction module, a normalization module, a reliability module, and a recognition module; the acquisition module is used to acquire SSVEP EEG signals. The preprocessing module is used to preprocess the SSVEP EEG signal to obtain a valid SSVEP EEG signal. The extraction module is used to replace the filter corresponding to each sub-band with M candidate filters based on the filter bank canonical correlation analysis algorithm, and extract the correlation coefficient group of each sub-band of the effective SSVEP EEG signal for each stimulus target based on the candidate filters. ,in k is the index of the stimulus target, K is the number of stimulus targets, and m is the index of the candidate filter; the normalization module is used to normalize the correlation array. Perform normalization processing to obtain the normalized correlation array. The credibility module is used to calculate the credibility parameters of each candidate filter in each sub-band based on the normalized correlation array for each stimulus target, and select the candidate filter with the smallest credibility parameter as the sub-filter of the sub-band; according to Calculate the confidence parameter for each candidate filter in each subband, where The maximum value, This is the second largest value; the recognition module is used to calculate the sub-band correlation coefficient of the SSVEP EEG signal for each stimulus target. The stimulus target corresponding to the maximum subband correlation coefficient is selected as the recognition result, whereby... This represents the normalized correlation coefficient of the nth sub-filter with respect to the kth stimulus target, where N represents the number of sub-filters. This represents the weight coefficient of the nth sub-filter.

8. A storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the adaptive EEG signal recognition method as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to cause the electronic device to perform the EEG signal adaptive recognition method according to any one of claims 1 to 6.

Images